fix: tune embedding dedup threshold to 0.935#293
Merged
Conversation
0.93 still caught false positives via star clustering — a hub entry similar to two distinct entries (at 0.9326 and 0.958) pulled all three into one cluster. 0.935 excludes 0.9326 while keeping genuine dupes. Empirical distribution (312 Nomic v1.5 entries): - 0.935+: all genuine duplicates - 0.92-0.935: false positives from same-subsystem entries - <0.92: related-but-distinct or noise Refs #292
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Refines the embedding dedup threshold from 0.93 → 0.935 to eliminate a false positive caused by star clustering.
Root Cause
At threshold 0.93, star clustering bridged two distinct entries through a hub:
0.935 excludes the 0.9326 pair while keeping all genuine duplicates (0.935+).
Threshold Tuning History
Refs #292 (adaptive threshold with user feedback — future improvement)